{"id":13958782,"url":"https://github.com/danielzuegner/robust-gcn","last_synced_at":"2025-10-27T01:20:14.823Z","repository":{"id":53830262,"uuid":"193091274","full_name":"danielzuegner/robust-gcn","owner":"danielzuegner","description":"Implementation of the paper \"Certifiable Robustness and Robust Training for Graph Convolutional Networks\".","archived":false,"fork":false,"pushed_at":"2020-12-07T15:16:05.000Z","size":6400,"stargazers_count":42,"open_issues_count":1,"forks_count":12,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-28T02:35:25.442Z","etag":null,"topics":["adversarial-robust","deep-learning","graph-neural-networks","robustness"],"latest_commit_sha":null,"homepage":"https://www.kdd.in.tum.de/research/robust-gcn/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/danielzuegner.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-06-21T12:05:44.000Z","updated_at":"2024-11-06T13:53:55.000Z","dependencies_parsed_at":"2022-08-22T08:00:53.540Z","dependency_job_id":null,"html_url":"https://github.com/danielzuegner/robust-gcn","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/danielzuegner/robust-gcn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielzuegner%2Frobust-gcn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielzuegner%2Frobust-gcn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielzuegner%2Frobust-gcn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielzuegner%2Frobust-gcn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/danielzuegner","download_url":"https://codeload.github.com/danielzuegner/robust-gcn/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielzuegner%2Frobust-gcn/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266221299,"owners_count":23894966,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["adversarial-robust","deep-learning","graph-neural-networks","robustness"],"created_at":"2024-08-08T13:01:51.690Z","updated_at":"2025-10-27T01:20:14.818Z","avatar_url":"https://github.com/danielzuegner.png","language":"Jupyter Notebook","funding_links":[],"categories":["图对抗攻击"],"sub_categories":["网络服务_其他"],"readme":"# Certifiable Robustness and Robust Training for GCN\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://www.in.tum.de/fileadmin/w00bws/daml/robust-gcn/figure_small.png\" width=\"400\"\u003e\n\u003c/p\u003e\n\nImplementation of the paper:   \n**[Certifiable Robustness and Robust Training for Graph Convolutional Networks](https://arxiv.org/abs/1906.12269)**\n\nby Daniel Zügner and Stephan Günnemann.   \nPublished at KDD'19, August 2019, Anchorage, USA\n\nCopyright (C) 2019   \nDaniel Zügner   \nTechnical University of Munich    \n\n## Additional resources\n[[Paper](https://arxiv.org/pdf/1906.12269.pdf) | [Poster](https://www.in.tum.de/fileadmin/w00bws/daml/robust-gcn/robust_gcn_poster.pdf) | [Slides (KDD 2019)](https://www.in.tum.de/fileadmin/w00bws/daml/robust-gcn/kdd2019_presentation_flattened.pdf)]\n\n## Run the code\n \nThe fastest way to try our code is to use the Jupyter notebook `demo.ipynb`.\n\n## Requirements\n* Python 3.6 or newer\n* `numpy`\n* `scipy`\n* `scikit-learn`\n* `pytorch`\n* `matplotlib` (for the demo notebook)\n\n`tqdm` is recommended for displaying progress bars.\n\n## Installation\n`python setup.py install`\n\nIf you just want to add a symbolic link to your package directory run   \n`python setup.py develop`\n \n## Contact\nPlease contact zuegnerd@in.tum.de in case you have any questions.\n\n\n## References\n### Datasets\nIn the `data` folder we provide the following datasets originally published by   \n#### Cora\nMcCallum, Andrew Kachites, Nigam, Kamal, Rennie, Jason, and Seymore, Kristie.  \n*Automating the construction of internet portals with machine learning.*   \nInformation Retrieval, 3(2):127–163, 2000.\n\nand the graph was extracted by\n\nBojchevski, Aleksandar, and Stephan Günnemann. *\"Deep gaussian embedding of   \nattributed graphs: Unsupervised inductive learning via ranking.\"* ICLR 2018.\n\n#### Citeseer\nSen, Prithviraj, Namata, Galileo, Bilgic, Mustafa, Getoor, Lise, Galligher, Brian, and Eliassi-Rad, Tina.   \n*Collective classification in network data.*   \nAI magazine, 29(3):93, 2008.\n#### PubMed\nSen, Prithviraj, Namata, Galileo, Bilgic, Mustafa, Getoor, Lise, Galligher, Brian, and Eliassi-Rad, Tina.   \n*Collective classification in network data.*   \nAI magazine, 29(3):93, 2008.\n\n### Graph Convolutional Networks\nOur implementation of the GCN algorithm is based on the authors' implementation,\navailable on GitHub [here](https://github.com/tkipf/gcn).\n\nThe paper was published as  \n\nThomas N Kipf and Max Welling. 2017.  \n*Semi-supervised classification with graph\nconvolutional networks.* ICLR (2017).\n\n## Cite\nPlease cite our paper if you use the model or this code in your own work:\n\n```\n@inproceedings{zugner2019robustgcn,\n  title={Certifiable Robustness and Robust Training for Graph Convolutional Networks},\n  author={Z{\\\"u}gner, Daniel and G{\\\"u}nnemann, Stephan},\n  booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery \\\u0026\\#38; Data Mining},\n  year={2019},\n  publisher = {ACM},\n  address = {New York, NY, USA},\nlocation = {Anchorage, United States},\n}\n\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanielzuegner%2Frobust-gcn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdanielzuegner%2Frobust-gcn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanielzuegner%2Frobust-gcn/lists"}